cd/entity/Reverse Direct Preference Optimization· home› entities› Reverse Direct Preference Optimization

grep -l @reverse direct preference optimization /news/*.json | wc -l → 2

Reverse Direct Preference Optimization

mentions 2 type Person feed RSS

// recent coverage 2 mentions

05:54

2026-07-08

letsdatascience.com

ai-safety

Amazon Nova Uses rDPO for Selective Unlearning

AWS introduced Reverse Direct Preference Optimization (rDPO) as a selective unlearning method for Amazon Nova, enabling customizable content moderation settings that reduce over-deflection in approved…

22:23

2026-07-06

aws.amazon.com

large-language-models

Teaching models to forget: Selective unlearning with Amazon Nova

Amazon Web Services introduced Reverse Direct Preference Optimization (rDPO), a novel unlearning technique behind Amazon Nova Customizable Content Moderation Settings (CCMS), which allows approved cus…

// co-occurs with top 8 entities

Amazon Nova 2 Amazon Web Services 1 Customizable Content Moderation Settings 1 Low-Rank Adaptation 1 Negative Preference Optimization 1 Direct Preference Optimization 1 Amazon 1 AWS 1